© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112671
    Prev
    Next
    INDEX
    Explanations

    please let

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confl
    -0.12
     ENG
    -0.10
     doubly
    -0.10
     blunt
    -0.10
     continental
    -0.10
     sno
    -0.10
     hypothetical
    -0.10
     fung
    -0.10
     Darling
    -0.10
     pov
    -0.10
    POSITIVE LOGITS
     whoever
    0.14
     posting
    0.11
     below
    0.11
     dumb
    0.10
     postings
    0.10
    -defined
    0.10
     defin
    0.09
     idiots
    0.09
     ther
    0.09
     compl
    0.09
    Activations Density 0.031%

    No Known Activations